© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13968
    Prev
    Next
    INDEX
    Explanations

    references to the word "about" indicating the subject matter or focus of the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "about"

    np_acts-logits-general · gemini-2.0-flash

    about followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acrylique
    -0.59
     jäsen
    -0.51
     financières
    -0.51
     termica
    -0.49
     fédé
    -0.49
     feroit
    -0.48
     miniaturka
    -0.48
     lanterna
    -0.45
     uovo
    -0.45
    ',\
    -0.44
    POSITIVE LOGITS
     about
    1.24
     ABOUT
    1.22
    about
    1.20
     About
    1.05
    bout
    1.05
    About
    1.04
    ABOUT
    0.99
    Bout
    0.98
     Bout
    0.91
     SOBRE
    0.82
    Activations Density 0.113%

    No Known Activations